Related papers: A Threat Modeling Framework for Evaluating Computi…
Stealth attacks pose potential risks to cyber-physical systems because they are difficult to detect. Assessing the risk of systems under stealth attacks remains an open challenge, especially in nonlinear systems. To comprehensively quantify…
Even though machine learning algorithms already play a significant role in data science, many current methods pose unrealistic assumptions on input data. The application of such methods is difficult due to incompatible data formats, or…
This work aims to show the applicability, and how, of privacy by design approach to biometric systems and the benefit of using formal methods to this end. Starting from a general framework that has been introduced at STM in 2014, that…
Analyzing privacy threats in software products is an essential part of software development to ensure systems are privacy-respecting; yet it is still a far from trivial activity. While there have been many advancements in the past decade,…
The importance of mission or safety critical software systems in many application domains of embedded systems is continuously growing, and so is the effort and complexity for reliability and safety analysis. Model driven development is…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
By exploiting the increasing surface attack of systems, cyber-attacks can cause catastrophic events, such as, remotely disable safety mechanisms. This means that in order to avoid hazards, safety and security need to be integrated,…
Ransomware represents a pervasive threat, traditionally countered at the operating system, file-system, or network levels. However, these approaches often introduce significant overhead and remain susceptible to circumvention by attackers.…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
Implementing large software, as software analyzers which aim to be used in industrial settings, requires a well-engineered software architecture in order to ease its daily development and its maintenance process during its lifecycle. If the…
Identifying drawbacks or insufficiencies in terms of safety is important also in early development stages of safety critical systems. In industry, development artefacts such as components or units, are often reused from existing artefacts…
The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…
Not long ago, it was thought that only software applications and general purpose digital systems i.e. computers were prone to various types of attacks against their security. The underlying hardware, hardware implementations of these…
Cyber-physical systems integrate computation, communication, and physical capabilities to interact with the physical world and humans. Besides failures of components, cyber-physical systems are prone to malignant attacks, and specific…
Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally crafted instances,…
This work presents ATLAS, an LLM-driven framework that bridges standardized threat modeling and property-based formal verification for System-on-Chip (SoC) security. Starting from vulnerability knowledge bases such as Common Weakness…
The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…
The rising use of Large Language Models (LLMs) to create and disseminate malware poses a significant cybersecurity challenge due to their ability to generate and distribute attacks with ease. A single prompt can initiate a wide array of…
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…
Model ensemble adversarial attack has become a powerful method for generating transferable adversarial examples that can target even unknown models, but its theoretical foundation remains underexplored. To address this gap, we provide early…